# PickScore

> Run PickScore by eval online or via API. from $0.00055833/sec, no setup.

**URL:** https://inference.sh/apps/eval/pickscore
**Last updated:** 2026-11-07

---

PickScore v1 — scores how well an image matches a text prompt (CLIP-H finetuned on Pick-a-Pic)

- app: `eval/pickscore`
- maker: [eval](https://inference.sh/apps/eval.md)
- category: [other](https://inference.sh/apps/category/other.md)
- tasks: [evaluation](https://inference.sh/apps/tag/evaluation.md)
- price: from $0.00055833/sec
- runs via: api, javascript and python sdk, belt cli, mcp

## pickscore API Guide

### About
pickscore v1 — scores how well an image matches a text prompt (clip-h finetuned on pick-a-pic)

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @3rx6bpcd pinned
result = client.run({
        "app": "eval/pickscore@3rx6bpcd",
        "input": {
            "prompt": "prompt",
            "images": [
                "https://example.com/file.png"
            ]
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @3rx6bpcd pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "eval/pickscore@3rx6bpcd",
        "input": {
            "prompt": "prompt",
            "images": [
                "https://example.com/file.png"
            ]
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "eval/pickscore@3rx6bpcd",
        "input": {
            "prompt": "prompt",
            "images": [
                "https://example.com/file.png"
            ]
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "eval/pickscore@3rx6bpcd",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **prompt** (string) *required*: Text prompt to score alignment against
- **images** (array) *required*: Images to score (1+)

#### Output
- **best_index** (integer): Index of the highest-scoring image
- **scores** (array): PickScore for each image (higher = better alignment)

## other other apps

- [Google Analytics](https://inference.sh/apps/google/analytics.md): from $0.00000277/sec
- [Google Search Console](https://inference.sh/apps/google/search-console.md): from $0.00000277/sec
- [HTTP Request](https://inference.sh/apps/infsh/http.md): from $0.00000277/sec
- [ArcFace Identity Similarity](https://inference.sh/apps/eval/arcface.md): from $0.00055833/sec
- [Gmail](https://inference.sh/apps/google/gmail.md): from $0.00000277/sec

## faq

### how much does PickScore cost?

from $0.00055833/sec. you pay per run from your inference shell credits. no subscription is required.

### how do I run PickScore via api?

call eval/pickscore with the javascript or python sdk, the rest api, or `belt app run eval/pickscore` from a terminal. the api reference on this page lists every input.

### who makes PickScore?

PickScore is made by eval and runs on inference shell. every eval app is listed at https://inference.sh/apps/eval.

### can my agent use PickScore?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to PickScore?

other other apps on inference shell include Google Analytics, Google Search Console, HTTP Request, ArcFace Identity Similarity. they run through the same api, so switching is a one-line change.